CN112702443B - A multi-star and multi-level cache allocation method and device for a satellite-ground cooperative communication system - Google Patents

Abstract

The invention provides a multi-star and multi-level cache allocation method and device for a satellite-ground cooperative communication system, including collecting content popularity information, buffer size information and transmission delay information required by the satellite-ground cooperative communication system to complete the cache allocation; The content service mode of star multi-level cache determines the system cache allocation problem; solves the cache allocation problem and obtains the optimal cache allocation strategy; based on the optimal cache allocation strategy, the content of the multi-star and multi-level edge servers in the system is cached to optimize the satellite Coordinated communication system performance. The method makes full use of the multi-satellite and multi-level cache architecture in the satellite-ground cooperative communication system, and provides users with edge content services through the collaboration between multi-level edge servers and between multiple satellite edge servers, which can effectively reduce The content service delay in the satellite-ground collaborative communication system, due to the long delay of the satellite-ground link, leads to the problem that the delay index cannot be achieved, ensuring the transmission of user delay-sensitive services.

Description

A multi-star and multi-level cache allocation method and device for a satellite-ground cooperative communication system

technical field

The present invention relates to the technical field of resource allocation in wireless communication, in particular to a method and device for allocating multi-star and multi-level buffers in a satellite-ground cooperative communication system.

Background technique

The satellite Internet is developing rapidly. The 6G white paper for next-generation mobile communications also proposes that 6G wireless networks will no longer be limited to the ground, but will realize seamless connection between ground, satellite and airborne networks. The satellite-ground collaborative communication system will be the next generation mobile Important development direction of communication. However, since users need to go through a satellite-to-ground link to access the Internet through satellites, a huge network delay is caused. Taking a low-orbit satellite with an orbit height of 1000km as an example, the satellite-to-ground link delay is 13ms, while the satellite-to-ground link delay of a 20,000km orbit medium-orbit satellite is as high as 270ms, which is far from reaching the delay of 1ms for 5G communication and 0.1ms for 6G communication. index.

The rapid development of global smart phones has promoted the development of mobile terminals and "edge processing", and edge processing systems have also emerged accordingly. Contrary to cloud processing, which concentrates all work in the cloud, by introducing edge servers, various processing tasks do not need to be uploaded to the cloud, but are completed at the local edge layer, which greatly improves processing efficiency, reduces user latency, and improves network response speed. Nowadays, multimedia content occupies an increasing proportion in communication, and unlike private data, multimedia content usually has high repetition. Therefore, some content is cached at the edge of the network, and when the user needs the corresponding content, the content is retrieved from the edge server to provide services, and there is no need to retrieve the content from the cloud, thereby effectively reducing the system delay. Since the cache of edge servers is limited, the optimal caching strategy needs to be determined according to user interests to minimize the service delay when users request content.

Possible buffer locations in the satellite-ground cooperative communication system include base stations, satellites, and ground stations, and multi-satellite cooperative buffering can be performed between satellites and satellites. The existing buffer allocation methods usually consider a simplified satellite communication model, such as only considering content caching on satellites, or only considering content caching at ground base stations. The existing methods lack a complete analysis of the overall system, and do not make full use of the multi-satellite and multi-level cache architecture in the satellite-ground cooperative communication system. In order to fully exploit the performance of the satellite-ground cooperative communication system and ensure the quality of user delay-sensitive services, it is necessary to propose an innovative cache allocation method using the multi-satellite and multi-level cache architecture in the satellite-ground cooperative communication system.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a method and device for allocating multi-star and multi-level caches in a satellite-ground collaborative communication system, using the multi-star and multi-level collaborative buffering to cache the service content required by users at the edge of the network, reducing the number of satellite-ground collaborative communication systems. The content service delay can alleviate the problem that the delay index cannot be reached due to the long delay of the satellite-ground link in the satellite-ground collaborative communication system, and ensure the transmission of user delay-sensitive services.

To achieve the above object, the present invention provides the following technical solutions:

The present application discloses a multi-star and multi-level cache allocation method for a satellite-ground collaborative communication system, comprising the following steps:

(1) Collect content popularity information, cache size information, and transmission delay information required by the satellite-ground cooperative communication system to complete cache allocation; the satellite-ground cooperative communication system includes a space segment and a ground segment; the space segment consists of several A satellite is formed, and the ground segment consists of a user, a base station, a ground station and a cloud server;

(2) Determine the system cache allocation problem based on the content service mode of multi-star and multi-level cache;

(3) Solve the cache allocation problem to obtain an optimal cache allocation strategy;

(3.1) Set the cached content of the ground station as the most popular content collection;

(3.2) According to the content popularity distribution and transmission delay information, the base station jointly caches the content set, and all base stations cache all the content in the content set;

(3.3) According to the content popularity distribution and transmission delay information, the satellites jointly cached content collection is obtained, and all satellites cache all the content in the content collection;

(3.4) Initially set the cache content of all base stations, initialize and set the cache content of all satellites, and calculate the average content service delay of the system under the initialization cache strategy;

(3.5) Keep the common cache content set unchanged for each base station satellite, solve the cache allocation problem, and obtain the optimal cache allocation strategy for the base station and satellite;

(3.6) Take the optimal buffer allocation strategy as the optimal buffer allocation strategy of the satellite-ground cooperative communication system;

(4) Content caching is performed on the multi-star and multi-level edge servers in the system based on the optimal cache allocation strategy to optimize the performance of the satellite-ground cooperative communication system.

Preferably, in the step (1), an inter-satellite link for content transmission between adjacent satellites is provided between the satellites, and each satellite is covered with several base stations and ground stations, and the satellite and the satellites within its coverage The base station, adjacent satellites and ground stations are connected; each base station is covered with several users, the base station is connected to the users within its coverage, the ground station is connected to the satellite and the cloud server, the satellite, base station , There is an edge server in the ground station that can cache content for content service.

Preferably, the method of collecting the content popularity information in the step (1) is to estimate and calculate based on the historical data of all the contents stored in the cloud server that are requested to obtain the probability that all the contents stored in the cloud server are requested by the user; The cache size information includes the cache size of the base station edge server, the cache size of the satellite edge server, and the cache size of the ground station edge server; the method of collecting the transmission delay information is the transmission delay information based on the historical transmission process, and the various states of the transmission channel. The delay information is estimated and calculated for the capacity, and the average transmission delay information of the content retrieved from different edge servers is calculated; Transmission delay information, transmission delay information of content retrieved by satellite from adjacent satellites, transmission delay information of content retrieved by satellite from ground station, transmission delay information of content retrieved by ground station from cloud server.

Preferably, the step (2) includes the following substeps:

(2.1) For each satellite, calculate the cache hit rate of different storage locations when users within its coverage area request content services; the cache hit rate includes the base station cache hit rate, the current satellite cache hit rate, and the adjacent satellite cache hit rate , ground station cache hit rate, cloud server cache hit rate;

(2.2) Calculate the average content service delay of the satellite based on the cache hit rate and the transmission delay information;

(2.3) Perform weighting processing on the average content service delay to obtain the weighted average content service delay of each satellite;

(2.4) Sum the weighted average content service delays of each satellite, and minimize the sum of the weighted average content service delays under the constraint of cache size to obtain the cache allocation problem.

Preferably, the sub-step (3.5) specifically includes the following iterative process:

(3.5.1) For each satellite, calculate the cache revenue of the content in the non-common cache content set cached by the base station within the coverage area; (3.5.2) For each satellite, update the cache of the base station within the coverage area to the common cache content set , and the content with the largest cache revenue in the non-common cache content set;

(3.5.3) For each satellite, calculate the cache revenue of the content in the satellite cache non-common cache content set;

(3.5.4) For each satellite, update the satellite's cache to the common cached content set, and the content with the highest cache revenue in the non-common cached content set;

(3.5.5) Calculate the average content service delay of the system after updating the cache policy;

(3.5.6) Determine whether the average content service delay after updating the cache policy is the same as the average content service delay before the update;

(3.5.7) If the same, the iteration ends;

(3.5.8) If different, repeat the above iteration process until the iteration ends.

Beneficial effects of the present invention: Compared with the prior art, a multi-star and multi-level cache allocation method for a satellite-ground cooperative communication system of the present invention first collects the content popularity information and cache size information required by the satellite-ground cooperative communication system to complete the cache allocation. and transmission delay information; then, the system cache allocation problem is determined based on the content service mode of multi-star and multi-level cache, the cache allocation problem is solved, and the optimal cache allocation strategy is obtained; The satellite-to-ground multi-level edge server performs content caching to optimize the performance of the satellite-to-ground collaborative communication system; this method can make full use of the multi-star and multi-level cache architecture in the satellite-to-ground collaborative communication system. The collaboration between satellite edge servers provides users with edge content services, which can effectively reduce the content service delay in the satellite-ground collaborative communication system, and alleviate the delay caused by the long delay of the satellite-ground link in the satellite-ground collaborative communication system. The problem that the index cannot be reached ensures the transmission of users' delay-sensitive services.

The features and advantages of the present invention will be described in detail through embodiments in conjunction with the accompanying drawings.

Description of drawings

1 is a flowchart of a method for allocating multi-star and multi-level caches in a satellite-ground cooperative communication system according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a satellite-ground cooperative communication system provided by an embodiment of the present invention;

3 is a flowchart of collecting content popularity information, cache size information, and transmission delay information required by the satellite-ground collaborative communication system to complete cache allocation provided by an embodiment of the present invention;

Fig. 4 is the flow chart of determining system cache allocation problem based on the content service mode of multi-star and multi-level cache provided by the example of the present invention;

5 is a flowchart of solving a cache allocation problem and obtaining an optimal cache allocation strategy provided by an embodiment of the present invention;

6 is a flowchart of maintaining a common cache content set for each base station satellite, solving a cache allocation problem, and obtaining an optimal cache allocation strategy for a base station and a satellite provided by an embodiment of the present invention;

7 is a schematic diagram of performance comparison of a method for allocating multi-star and multi-level caches in a satellite-ground cooperative communication system according to an embodiment of the present invention;

FIG. 8 is a structural block diagram of an apparatus for allocating multi-star and multi-level caches in a satellite-ground cooperative communication system according to an embodiment of the present invention.

In the figure: 11-information collection module; 12-cache allocation problem determination module; 13-optimal cache solution module; 14-cache allocation module.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below through the accompanying drawings and embodiments. However, it should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the scope of the present invention. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present invention.

To facilitate understanding of this embodiment, a method for allocating multi-star and multi-level caches in a satellite-ground cooperative communication system disclosed in the embodiment of the present invention is first introduced in detail.

Example 1:

A method for allocating multi-star and multi-level caches in a satellite-ground cooperative communication system, with reference to FIG. 1 , the method includes:

S101. Collect content popularity information, cache size information, and transmission delay information required by the satellite-ground cooperative communication system to complete cache allocation;

In the embodiment of the present invention, the execution body of the method is a resource management center. Specifically, if the resource management center is set on the satellite, the satellite is the execution subject of the method, and if the resource management center is set at the ground station, the ground station is the execution subject of the method.

Specifically, in the embodiment of the present invention, the satellite-ground collaborative communication system provides content transmission services for terrestrial users. The terrestrial users are located outside the coverage of traditional terrestrial cellular networks and can only obtain content from a cloud server through satellites. Therefore, some content is cached in the edge server of the satellite-ground collaborative communication system. When the user needs the corresponding content, the content is retrieved from the edge server to provide services without retrieving the content from the cloud, thereby effectively reducing the system delay.

The process of collecting content popularity information, cache size information, and transmission delay information required by the satellite-ground cooperative communication system to complete cache allocation will be described in detail below, and will not be repeated here.

S102. Determine the system cache allocation problem based on the content service mode of the multi-star and multi-level cache, wherein the content service mode of the multi-star and multi-level cache indicates that the content is cached through the cooperation of base stations, satellites, ground stations and multi-satellite cooperation to provide users with Content service, cache allocation problem means to minimize the average content service delay of all users under the constraint of cache size. The cache allocation problem includes content popularity information, cache size information, and transmission delay information;

After obtaining the content popularity information, cache size information, and transmission delay information of the satellite-ground cooperative communication system, the system cache allocation problem is determined based on the content service mode of multi-star and multi-level cache. The content service mode of multi-star and multi-level cache indicates that the Base stations, satellites, ground stations and multi-satellites cooperate to cache content to provide users with content services. The cache allocation problem includes content popularity information, cache size information, and transmission delay information. Minimize the average content serving delay for all users under size constraints. The process will be described in detail below, and will not be repeated here.

S103, solve the cache allocation problem to obtain an optimal cache allocation strategy;

After the cache allocation problem is obtained, the cache allocation problem is solved to obtain the optimal cache allocation strategy. The process will be described in detail below, and will not be repeated here.

S104, based on the optimal cache allocation strategy, perform content caching on the multi-star and multi-level edge servers in the system to optimize the performance of the satellite-ground collaborative communication system.

Existing buffer allocation methods usually consider simplified satellite communication models, such as only content caching on satellites, or only content caching at ground base stations, lack of complete analysis of the overall system, and insufficient use of satellite-ground cooperative communication systems. The multi-star and multi-level cache architecture, the system performance is not good. Compared with the existing cache allocation method based on the simplified satellite communication model, in the multi-satellite and multi-level cache allocation method of the satellite-ground cooperative communication system according to the embodiment of the present invention, the content popularity required by the satellite-ground cooperative communication system to complete the cache allocation is first collected. Then, based on the content service mode of multi-star and multi-level cache, the system cache allocation problem is determined, the cache allocation problem is solved, and the optimal cache allocation strategy is obtained; finally, based on the optimal cache The allocation strategy caches the content of the multi-star and multi-level edge servers in the system to optimize the performance of the satellite-ground collaborative communication system. The method can make full use of the multi-satellite and multi-level cache architecture in the satellite-ground cooperative communication system, and provide users with edge content services through the collaboration between multi-level edge servers and among multiple satellite edge servers, which can effectively reduce The content service delay in the small satellite-ground cooperative communication system alleviates the problem that the delay index cannot be reached due to the long delay of the satellite-ground link in the satellite-ground cooperative communication system, and ensures the transmission of user delay-sensitive services.

The above content briefly introduces the multi-star and multi-level cache allocation method of the satellite-ground cooperative communication system, and the specific content involved is described in detail below.

In an optional embodiment, referring to FIG. 2 , the satellite-ground cooperative communication system includes:

The satellite-ground cooperative communication system includes space segment and ground segment;

表示当前卫星

的

跳相邻卫星集合，

跳相邻卫星指通过

次星间链路传输能够到达的相邻卫星；The space segment consists of multiple satellites. There is an inter-satellite link between satellites, and content can be transmitted with adjacent satellites through the inter-satellite link. The adjacent satellite refers to the satellite that has an inter-satellite link with the current satellite. any currently concerned satellite, used to distinguish it from neighboring satellites,

Indicates the current satellite

of

Hop the set of adjacent satellites,

Hopping adjacent satellites means passing

Adjacent satellites reachable by secondary inter-satellite link transmissions;

Satellites are connected to base stations, adjacent satellites, and ground stations within their coverage. There are edge servers in satellites that can cache content for content services. Satellites provide content transmission services to base stations within their coverage. The inter-satellite link obtains the corresponding content from the adjacent satellites, and can also obtain the corresponding content from the ground station;

The ground segment consists of users, base stations, ground stations and cloud servers;

The user is only connected to the subordinate base station, and the subordinate base station means that the user is located within the coverage of the base station, and the user obtains content transmission services through the base station;

A base station is connected to users within its coverage area and subordinate satellites. A subordinate satellite means that the base station is located within the coverage area of the satellite. There is an edge server in the base station that can cache content for content services. The base station provides content transmission services to users within its coverage area. For unstored content, the corresponding content can be obtained from the subordinate satellite;

The ground station is connected to the satellite and the cloud server. There is an edge server in the ground station, which can cache content for content services. The ground station provides content transmission services for the satellite. For the content not stored in the ground station, the corresponding content can be obtained from the cloud server;

The cloud server stores all content and provides content services for the ground station;

覆盖范围内的任意用户，用户请求任意内容

时的服务过程如下：to any satellite

Any user within the coverage area, the user requests any content

The service process is as follows:

缓存在用户的从属基站中，从属基站直接为用户提供内容传输服务；If the content

It is cached in the user's subordinate base station, and the subordinate base station directly provides the user with content transmission services;

未缓存在用户的从属基站中，缓存在卫星

中，卫星

首先将该内容传输给从属基站，然后从属基站为用户提供内容传输服务；If the content

Not cached in the user's subordinate base station, cached in the satellite

medium, satellite

First transmit the content to the subordinate base station, and then the subordinate base station provides the content transmission service for the user;

未缓存在用户的从属基站与卫星

中，缓存在卫星

的相邻卫星中，卫星

首先从相邻卫星获取该内容，然后卫星

将该内容传输给从属基站，接着从属基站为用户提供内容传输服务；If the content

Not cached in the user's subordinate base stations and satellites

, cached in the satellite

Among the adjacent satellites, the satellite

First get that content from neighboring satellites, then satellites

The content is transmitted to the subordinate base station, and then the subordinate base station provides the user with content transmission service;

未缓存在用户的从属基站、卫星

、卫星

的相邻卫星中，缓存在地面站中，卫星

首先从地面站获取该内容，然后卫星

将该内容传输给从属基站，接着从属基站为用户提供内容传输服务；If the content

Not cached in the user's subordinate base stations, satellites

,satellite

in adjacent satellites, cached in the ground station, the satellite

First get that content from the ground station, then the satellite

The content is transmitted to the subordinate base station, and then the subordinate base station provides the user with content transmission service;

未缓存在用户的从属基站、卫星

、卫星

的相邻卫星、地面站中，缓存在云端服务器中，地面站首先从云端服务器获取该内容，然后卫星

从地面站获取该内容，接着卫星

将该内容传输给从属基站，最后从属基站为用户提供内容传输服务。If the content

Not cached in the user's subordinate base stations, satellites

,satellite

The adjacent satellites and ground stations are cached in the cloud server. The ground station first obtains the content from the cloud server, and then the satellite

Get this content from the ground station, then the satellite

The content is transmitted to the subordinate base station, and finally the subordinate base station provides a content transmission service for the user.

Optionally, referring to FIG. 3 , the content popularity information, cache size information, and transmission delay information required by the satellite-ground cooperative communication system to complete the cache allocation include:

S201. Perform an estimation calculation based on the requested historical data of the content to obtain the popularity distribution information of the content;

，其中前

种内容为最流行的前

种内容，第

种内容为剩余所有内容集合。流行度分布信息指内容被用户请求的概率，表示为

，不同内容的流行度分布以降序排序，满足

，且所有内容流行度分布之和为1，表示为

。The content collection is all the content stored in the cloud server, expressed as

, of which the former

content for the most popular ex

content, the

This kind of content is the collection of all the remaining content. Popularity distribution information refers to the probability of content being requested by users, expressed as

, the popularity distribution of different content is sorted in descending order, satisfying

, and the sum of all content popularity distributions is 1, which is expressed as

.

S202. Collect cache size information of each edge server in the satellite-ground collaborative communication system;

、卫星边缘服务器缓存大小

、地面站边缘服务器缓存大小

，考虑地面站缓存较为充足，地面站的缓存大小满足

。The collected cache size information includes: base station edge server cache size

, Satellite edge server cache size

, Ground station edge server cache size

, considering that the ground station buffer is relatively sufficient, the buffer size of the ground station is sufficient

.

S203, performing delay information estimation and calculation based on the delay information of the historical transmission process and the ergodic capacity of each state of the transmission channel, and calculating the average transmission delay information of the content retrieved from different edge servers;

、基站从卫星取回内容的传输延时信息

、卫星从相邻卫星取回内容的传输延时信息

、卫星从地面站取回内容的传输延时信息

、地面站从云端服务器取回内容的传输延时信息

。The collected transmission delay information includes: the transmission delay information of the content retrieved by the user from the base station

, the transmission delay information of the content retrieved by the base station from the satellite

, the transmission delay information of the content retrieved by the satellite from the adjacent satellite

, The transmission delay information of the content retrieved by the satellite from the ground station

, The ground station retrieves the transmission delay information of the content from the cloud server

.

Optionally, referring to FIG. 4 , determining the system cache allocation problem based on the content service mode of multi-star and multi-level cache includes:

S301, for each satellite, calculate the cache hit rate of different storage locations when the user requests content service within its coverage, wherein the cache hit rate refers to the probability that the content requested by the user is cached at the corresponding location;

所服务的用户，请求任意内容时：for satellite

The served user, when requesting arbitrary content:

，其中，

为卫星

覆盖范围内基站所缓存内容的集合，

为基站缓存分配因子，

表示内容

缓存在卫星

覆盖范围内基站内，反之未缓存。The base station cache hit probability is

,in,

for satellite

A collection of content cached by base stations within the coverage area,

allocation factor for base station cache,

show content

cached on satellite

Within the coverage area of the base station, otherwise it is not cached.

缓存命中概率为

，其中

为卫星

所缓存内容的集合，

为卫星缓存分配因子，

表示内容

缓存在卫星内，反之未缓存。Base station cache miss, satellite

The cache hit probability is

,in

for satellite

a collection of cached content,

assign factor to satellite cache,

show content

Cached in the satellite, otherwise not cached.

缓存未命中，卫星

的

跳相邻卫星缓存命中概率为

，Base station cache miss, satellite

cache miss, satellite

of

The probability of a hop adjacent satellite cache hit is

,

为卫星

的

跳相邻卫星所缓存内容的集合，

表示内容

缓存在卫星

跳相邻卫星内，反之未缓存。in

for satellite

of

skip the collection of cached content by neighboring satellites,

show content

cached on satellite

Jump within adjacent satellites, otherwise uncached.

种内容，基站缓存未命中，卫星

缓存未命中，卫星

相邻卫星缓存未命中，地面站缓存命中概率为

，其中

为最大的星间跳数。The ground station cache is relatively large, before the cache

content, base station cache miss, satellite

cache miss, satellite

Adjacent satellite cache misses, the ground station cache hit probability is

,in

is the maximum number of inter-satellite hops.

缓存未命中，卫星

相邻卫星缓存未命中，地面站缓存未命中，云端服务器的缓存命中概率为

。Base station cache miss, satellite

cache miss, satellite

The adjacent satellite cache misses, the ground station cache misses, and the cache hit probability of the cloud server is

.

S302. For each satellite, calculate the average content service delay of the satellite based on the cache hit rate and transmission delay information, where the average content service delay of the satellite refers to the average content service delay when users request content services within the coverage of the satellite Time;

平均内容服务延时为：satellite

The average content service latency is:

S303. Perform weighting processing on the average content service delay to obtain the weighted average content service delay of each satellite;

的加权平均内容服务延时为

。satellite

The weighted average content serving latency is

.

S304, summing the weighted average content service delays of each satellite, and minimizing the sum of the weighted average content service delays under the constraint of the cache size, to obtain a cache allocation problem, wherein the cache size constraint refers to the base station and the satellite edge server The stored content cannot exceed the cache size;

Get the cache allocation problem as:

为所有基站和卫星的缓存分配因子集合。in

Allocate the set of factors for the caches of all base stations and satellites.

Optionally, referring to FIG. 5, the cache allocation problem is solved, and the optimal cache allocation strategy is obtained including:

S401. Set the cached content of the ground station as the most popular content collection;

个内容，表示为

。Ground station cache is the most popular

content, expressed as

.

S402, according to the content popularity distribution and transmission delay information, calculate and obtain the content set jointly cached by the base stations, and all base stations cache all the content in the content set;

The common cache content of all base stations is

计算所用算式如下：in

The formula used for the calculation is as follows:

。

.

S403. Calculate and obtain a satellite common cache content set according to the content popularity distribution and transmission delay information, and all satellites cache all the content in the content set;

The common cache content of all satellites is

和

计算所用算式如下：in,

and

The formula used for the calculation is as follows:

S404, initialize and set the cached content of all base stations and satellites as the most popular content;

，初始化设定所有卫星的缓存内容为

，计算初始化缓存策略下的系统平均内容服务延时。Initially set the cache content of all base stations as

, initialize the cache content of all satellites as

, calculate the average content service delay of the system under the initialized caching strategy.

S405. Keep the common cache content set unchanged for each base station satellite, solve the cache allocation problem, and obtain an optimal cache allocation strategy for the base station and the satellite;

不变，每一个卫星将保持缓存内容集合

不变，求解得到最优缓存分配策略，最小化加权平均内容服务延时。下文中再对该过程进行详细描述。In solving the buffer allocation problem, each base station will maintain a set of buffer contents

unchanged, each satellite will maintain a collection of cached content

unchanged, the optimal cache allocation strategy is obtained by solving, and the weighted average content service delay is minimized. The process will be described in detail below.

S406. Use the obtained optimal buffer allocation strategy as the optimal buffer allocation strategy of the satellite-ground cooperative communication system.

Optionally, referring to FIG. 6 , keep the common cache content set unchanged for each base station satellite, solve the cache allocation problem, and obtain the optimal cache allocation strategy for the base station and the satellite, including:

Perform the following iterative process:

S501, for each satellite, calculate the cache revenue of the content in the non-common cache content set cached by the base station within the coverage;

，对内容集合

中每一个内容

，计算缓存收益

，缓存收益

为卫星

覆盖范围内的基站缓存内容

与未缓存内容

相比，所带来的系统平均内容服务延时的减小量。令

表示卫星

覆盖范围内的基站未缓存内容

时的系统平均内容服务延时，

表示卫星

覆盖范围内的基站缓存内容

时的系统平均内容服务延时，可得

。for each satellite

, for the content collection

each content

, calculate the cache revenue

, cache revenue

for satellite

Base station cache content within coverage

with uncached content

In comparison, the resulting reduction in the average content service delay of the system. make

Represents a satellite

Base stations in range are not caching content

The average content service delay of the system when

Represents a satellite

Base station cache content within coverage

The average content service delay of the system when

.

计算方法如下：

The calculation method is as follows:

缓存在卫星

中，缓存收益为

；If the content

cached on satellite

, the cache revenue is

;

最近缓存为卫星的

的

跳相邻卫星，缓存收益为

，其中，最近缓存指缓存有该内容且取回该内容延时最低的缓存位置；If the content

Recently cached as satellite

of

Hopping adjacent satellites, the cache revenue is

, where the most recent cache refers to the cache location where the content is cached and the delay in retrieving the content is the lowest;

未缓存在卫星

及其相邻卫星中，缓存收益为

；like

Not cached on satellite

and its adjacent satellites, the cache revenue is

;

S502, for each satellite, update the cache of the base station within the coverage to a common cache content set, and the content with the largest cache revenue in the non-common cache content set;

，将卫星

覆盖范围内基站的缓存更新为

，其中

为

中缓存收益最大内容，直至达到基站缓存大小上限。for each satellite

, the satellite

The cache of the base station in the coverage area is updated to

,in

for

The most profitable content is cached in the middle, until the upper limit of the base station cache size is reached.

表示集合

中的内容数量，由于基站的缓存大小为

，剩余可缓存其余内容的缓存大小为

，从而集合

为

中缓存收益最大的

个内容。use

Represents a collection

The amount of content in , since the base station's cache size is

, the remaining cache size that can cache the rest of the content is

, so that the collection

for

The most profitable cache

content.

S503, for each satellite, calculate the cache revenue of the content in the satellite cache non-common cache content set;

，对内容集合

中每一个内容

，计算缓存收益

，其中，计算

所用算式如下：for each satellite

, for the content collection

each content

, calculate the cache revenue

, which calculates

The formula used is as follows:

为卫星

缓存内容

与未缓存内容

相比，所带来的系统平均内容服务延时的减小量。令

表示卫星

未缓存内容

时的系统平均内容服务延时，

表示卫星

缓存内容

时的系统平均内容服务延时，可得

。Cache revenue

for satellite

cache content

with uncached content

In comparison, the resulting reduction in the average content service delay of the system. make

Represents a satellite

Content not cached

The average content service delay of the system when

Represents a satellite

cache content

The average content service delay of the system when

.

为来自于卫星

覆盖范围内用户收益，也即卫星

缓存内容

与未缓存内容

相比，卫星

覆盖范围内用户平均内容服务延时的减小量。

from satellite

Benefit of users within the coverage area, i.e. satellite

cache content

with uncached content

compared to satellite

The amount of reduction in the average content service latency of users within the coverage area.

为来自于卫星

相邻

跳卫星用户收益，也即卫星

缓存内容

与未缓存内容

相比，卫星

相邻

跳卫星用户平均内容服务延时的减小量。

from satellite

adjacent

Jump satellite user revenue, aka satellite

cache content

with uncached content

compared to satellite

adjacent

The amount of reduction in average content service latency for hop-satellite users.

的计算方法如下：

is calculated as follows:

缓存在卫星

覆盖范围内基站中，

；like

cached on satellite

In the base station within the coverage area,

;

最近缓存为卫星

的

跳相邻卫星，

；like

Recently cached as satellite

of

hop adjacent satellites,

;

未缓存在卫星

覆盖范围内基站及卫星

的相邻卫星中，

。like

Not cached on satellite

Base stations and satellites within coverage

among the adjacent satellites,

.

任意

跳相邻卫星

，假设卫星

未缓存任何内容，累加计算

。for satellite

any

hop adjacent satellites

, assuming the satellite

Nothing is cached, cumulative calculation

.

的每一个

跳相邻卫星

，

的计算方法如下：to satellite

each of

hop adjacent satellites

,

is calculated as follows:

缓存在卫星

，或者卫星

覆盖范围内基站中，

；like

cached on satellite

, or satellite

In the base station within the coverage area,

;

最近缓存为卫星

的

跳相邻卫星，

；like

Recently cached as satellite

of

hop adjacent satellites,

;

最近缓存为卫星

的

跳相邻卫星，

；like

Recently cached as satellite

of

hop adjacent satellites,

;

未缓存在卫星

覆盖范围内基站及卫星

的相邻卫星中，

。like

Not cached on satellite

Base stations and satellites within coverage

among the adjacent satellites,

.

S504, for each satellite, update the cache of the satellite to a common cached content set, and the content with the largest cache revenue in the non-common cached content set;

，将其缓存更新为

，其中

为

中缓存收益最大内容，直至达到卫星缓存大小上限。for each satellite

, update its cache to

,in

for

The most profitable content is cached in the medium, until the maximum size of the satellite cache is reached.

表示集合

中的内容数量，由于卫星的缓存大小为

，剩余可缓存其余内容的缓存大小为

，从而集合

为

中缓存收益最大的

个内容。use

Represents a collection

The amount of content in , since the satellite's cache size is

, the remaining cache size that can cache the rest of the content is

, so that the collection

for

The most profitable cache

content.

S505. Calculate the average content service delay of the system after updating the cache policy;

，其中

的计算过程可参见之前方法实施例，在此不再赘述。Calculate the average content service delay of the system after updating the cache policy

,in

For the calculation process of , reference may be made to the previous method embodiments, which will not be repeated here.

S506, judging whether the average content service delay after updating the cache policy is the same as the average content service delay before updating;

S507, if the same, the iteration ends;

S508. If not, repeat the above iteration process until the iteration ends.

The invention proposes a multi-star and multi-level cache allocation method and device for a satellite-ground cooperative communication system. The multi-star and multi-level cooperative cache is used to cache the service content required by the user at the network edge to provide edge content service. The invention calculates the common cache content of all base stations based on the fixed cache strategy of the base station, calculates the common cache content of all satellites based on the satellite fixed cache strategy, and calculates the cache income of the content other than the common cache content to obtain each base station and each The content cached by the satellite outside the common cache is finally solved to obtain the system cache strategy with the smallest average content service delay.

为100，卫星缓存

为200，卫星数量为100，用户从基站取回内容的延时

为20 ms，基站从卫星取回内容的延时

为100 ms，卫星从相邻卫星取回内容的延时

为40 ms，卫星从地面站取回内容的延时

为90 ms，地面站从云端服务器取回内容的延时

为200 ms。内容流行度分布采用因子为0.7的zipf分布，计算方式为

。参考图7（所提出的多星多级缓存分配方法与最流行缓存分配方法以及随机缓存分配方法性能对比），可以看出所提出的缓存分配方法能够有效减小星地协同通信系统中内容服务延时，相比于最流行缓存分配方法可减小20%的平均内容服务延时。The schematic diagram of the satellite-ground cooperative communication system of the present invention is shown in Figure 2, in which the total number of contents is set in the range of 500-5000, and the base station caches

is 100, satellite cache

is 200, the number of satellites is 100, the delay for the user to retrieve the content from the base station

is 20 ms, the delay for the base station to retrieve the content from the satellite

is 100 ms, the delay for satellites to retrieve content from adjacent satellites

is 40 ms, the delay for the satellite to retrieve the content from the ground station

is 90 ms, the delay for the ground station to retrieve the content from the cloud server

is 200 ms. The content popularity distribution adopts a zipf distribution with a factor of 0.7, and is calculated as

. Referring to Figure 7 (performance comparison of the proposed multi-star and multi-level cache allocation method with the most popular cache allocation method and random cache allocation method), it can be seen that the proposed cache allocation method can effectively reduce the content service delay in the satellite-ground cooperative communication system. When compared to the most popular cache allocation method, the average content serving latency can be reduced by 20%.

Embodiment 2:

A multi-star and multi-level cache allocation device of a satellite-ground cooperative communication system, with reference to FIG. 8 , the device includes:

The information collection module 11 is used to collect the content popularity information, cache size information and transmission delay information required by the satellite-ground cooperative communication system to complete the cache allocation;

The cache allocation problem determination module 12 is used to determine the system cache allocation problem based on the content service mode of the multi-star and multi-level cache, wherein the content service mode of the multi-star and multi-level cache indicates that the base station, satellite, ground station coordination and multi-satellite coordination Carry out content caching to provide content services for users. The cache allocation problem means that the average content service delay of all users is minimized under the condition that the cache size constraint is satisfied. The cache allocation problem includes content popularity information, cache size information, and transmission delay information. ;

The optimal cache solution module 13 is used to solve the cache allocation problem to obtain an optimal cache allocation strategy;

The cache allocation module 14 is configured to cache the content of the multi-star and multi-level edge servers in the system based on the optimal cache allocation strategy, so as to optimize the performance of the satellite-ground collaborative communication system.

In the multi-star and multi-level cache allocation device of the satellite-ground cooperative communication system in the embodiment of the present invention, the content popularity information, buffer size information and transmission delay information required by the satellite-ground cooperative communication system to complete the cache allocation are first collected; The content service mode of star multi-level cache determines the system cache allocation problem, solves the cache allocation problem, and obtains the optimal cache allocation strategy; Optimize the performance of the satellite-ground cooperative communication system. The device can make full use of the multi-satellite and multi-level cache architecture in the satellite-ground collaborative communication system, and provide users with edge content services through the collaboration between multi-level edge servers and among multiple satellite edge servers, which can effectively reduce The content service delay in the small satellite-ground cooperative communication system alleviates the problem that the delay index cannot be reached due to the long delay of the satellite-ground link in the satellite-ground cooperative communication system, and ensures the transmission of user delay-sensitive services.

Optionally, the information collection module includes:

a content popularity collection unit, configured to perform estimation calculation based on the requested historical data of the content, and obtain the content popularity distribution information, wherein the content refers to all the content stored in the cloud server;

The system cache information collection unit is used to collect cache size information of each edge server in the satellite-ground cooperative communication system, wherein the cache size information includes: base station edge server cache size information, satellite edge server cache size information, and ground station edge server cache size information;

The system transmission delay information collection unit is used to estimate and calculate the delay information based on the delay information of the historical transmission process and the ergodic capacity of each state of the transmission channel, and calculate the average transmission delay information of the content retrieved from different edge servers, wherein The transmission delay information includes: the transmission delay information of the content retrieved by the user from the base station, the transmission delay information of the content retrieved by the base station from the satellite, the transmission delay information of the content retrieved by the satellite from the adjacent satellite, and the transmission delay information of the satellite retrieved from the ground station. The transmission delay information of the content is returned, and the transmission delay information of the content retrieved by the ground station from the cloud server.

Optionally, the cache allocation problem determination module includes:

The cache hit rate calculation unit is used to calculate, for each satellite, the cache hit rate of different storage locations when users within its coverage area request content services, wherein the cache hit rate refers to the probability that the content requested by the user is cached in the corresponding location;

The average content service delay calculation unit is used to calculate the average content service delay of the satellite based on the cache hit rate and transmission delay information for each satellite, where the average content service delay of the satellite refers to the user request within the coverage of the satellite. Average content service delay during content service;

a weighted processing unit, configured to perform weighted processing on the average content service delay to obtain the weighted average content service delay of each satellite;

The minimization unit is used to sum the weighted average content service delay of each satellite, and minimize the sum of the weighted average content service delay under the condition of the cache size constraint to obtain the cache allocation problem, where the cache size constraint refers to the base station and satellite edge servers cannot store more than the cache size.

Optionally, the optimal cache solution module includes:

The ground station fixed cache calculation unit is used to set the ground station cache content as the most popular content set;

The base station fixed cache calculation unit is used to calculate and obtain the common cache content set of the base station according to the content popularity distribution and transmission delay information, and all base stations cache all the content in the content set;

The satellite fixed cache calculation unit is used to calculate and obtain the satellite common cache content set according to the content popularity distribution and transmission delay information, and all satellites cache all the content in the content set;

The cache initialization unit is used to initialize and set the cache content of all base stations and satellites as the most popular content;

The solving unit is used to keep the common cache content set unchanged for each base station satellite, solve the cache allocation problem, and obtain the optimal cache allocation strategy of the base station and the satellite;

The setting unit is used for taking the obtained optimal buffer allocation strategy as the optimal buffer allocation strategy of the satellite-ground cooperative communication system.

Optionally, the solving unit includes:

Perform the following iterative process:

For each satellite, calculate the cache revenue of the content in the non-common cache content set cached by the base station within the coverage area;

For each satellite, update the cache of the base station within the coverage area to the common cache content set, and the content with the largest cache benefit in the non-common cache content set;

For each satellite, calculate the cache revenue of the satellite cache content in the non-co-cached content set;

For each satellite, update the satellite's cache to the common cached content set, and the content with the largest cache benefit in the non-common cached content set;

Calculate the average content service delay of the system after updating the cache policy;

Determine whether the average content service delay after updating the cache policy is the same as the average content service delay before the update;

If they are the same, the iteration ends;

If not, repeat the above iterative process until the iteration ends.

For the specific content in the second embodiment, reference may be made to the specific description in the above-mentioned first embodiment, which will not be repeated here.

The computer program product of the method and device for allocating multi-star and multi-level caches in a satellite-ground cooperative communication system provided by the embodiment of the present invention includes a computer-readable storage medium storing program codes, and the instructions included in the program codes can be used to execute the foregoing methods. For the specific implementation of the method described in the embodiment, reference may be made to the method embodiment, which will not be repeated here.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the system and device described above, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements or improvements made within the spirit and principles of the present invention shall be included in the protection of the present invention. within the range.

Claims (5)

1. A multi-satellite multi-level cache allocation method for a satellite-ground cooperative communication system is characterized by comprising the following steps:

(1) collecting content popularity information, cache size information and transmission delay information required by the satellite-ground cooperative communication system to finish cache allocation; the satellite-ground cooperative communication system comprises a space section and a ground section; the space section consists of a plurality of satellites, and the ground section consists of a user, a base station, a ground station and a cloud server;

(2) determining a system cache allocation problem based on a content service mode of multi-star multi-level cache;

(3) solving the cache allocation problem to obtain an optimal cache allocation strategy;

(3.1) setting the cached content of the ground station as a content set with the highest popularity;

(3.2) calculating to obtain a common cache content set of the base stations according to the content popularity distribution and the transmission delay information, wherein all the base stations cache all the content in the content set;

(3.3) calculating to obtain a satellite common cache content set according to the content popularity distribution and the transmission delay information, wherein all the satellites cache all the content in the content set;

(3.4) initializing and setting the cache contents of all base stations, initializing and setting the cache contents of all satellites, and calculating the average content service delay of the system under the initialization cache strategy;

(3.5) keeping a common cache content set unchanged for each base station satellite, and solving the cache allocation problem to obtain an optimal cache allocation strategy of the base station and the satellite;

(3.6) using the optimal cache allocation strategy as the optimal cache allocation strategy of the satellite-ground cooperative communication system;

(4) and performing content caching on the multi-satellite multi-level edge server in the system based on the optimal caching distribution strategy so as to optimize the performance of the satellite-ground cooperative communication system.

2. The multi-satellite multi-level buffer allocation method for the satellite-ground cooperative communication system according to claim 1, wherein in the step (1), inter-satellite links for content transmission of adjacent satellites are provided between the satellites, each satellite is covered with a plurality of base stations and ground stations, and the satellite is connected with the base stations, the adjacent satellites and the ground stations within the coverage range of the satellite; each base station is covered with a plurality of users, the base stations are connected with the users in the coverage range of the base stations, the ground station is connected with the satellite and the cloud server, and the satellite, the base stations and the ground station are provided with edge servers capable of caching content for content service.

3. The multi-satellite multi-level cache allocation method for the satellite-ground cooperative communication system according to claim 2, wherein the content popularity information is collected in the step (1) by performing estimation calculation based on history data of all content requests stored in the cloud server, so as to obtain a probability that all content stored in the cloud server is requested by a user; the cache size information comprises the cache size of a base station edge server, the cache size of a satellite edge server and the cache size of a ground station edge server; the mode of collecting the transmission delay information is to estimate and calculate the delay information based on the transmission delay information of the historical transmission process and the ergodic capacity of the transmission channel, and calculate the average transmission delay information of the contents retrieved from different edge servers; the transmission delay information includes: the method includes the steps that a user retrieves transmission delay information of content from a base station, the base station retrieves transmission delay information of the content from a satellite, the satellite retrieves transmission delay information of the content from an adjacent satellite, the satellite retrieves transmission delay information of the content from a ground station, and the ground station retrieves transmission delay information of the content from a cloud server.

4. A multi-satellite multi-level buffer allocation method for a satellite-to-ground cooperative communication system according to claim 3, wherein the step (2) comprises the following sub-steps:

(2.1) calculating cache hit rates of different storage positions when a user requests content services in the coverage area of each satellite; the cache hit rate comprises a base station cache hit rate, a current satellite cache hit rate, an adjacent satellite cache hit rate, a ground station cache hit rate and a cloud server cache hit rate;

(2.2) calculating the satellite average content service delay based on the cache hit rate and the transmission delay information;

(2.3) weighting the average content service delay to obtain weighted average content service delay of each satellite;

and (2.4) summing the weighted average content service delays of all the satellites, and minimizing the sum of the weighted average content service delays under the constraint condition of the cache size to obtain the cache allocation problem.

5. The multi-satellite multi-level buffer allocation method for the satellite-to-ground cooperative communication system according to claim 1, wherein the sub-step (3.5) specifically comprises the following iterative process:

(3.5.1) calculating the caching profit of the content in the non-common caching content set cached by the base station in the coverage area for each satellite;

(3.5.2) for each satellite, updating the cache of the base station in the coverage range into a common cache content set and cache contents with maximum profit in a non-common cache content set;

(3.5.3) for each satellite, calculating a cache gain for the satellite to cache content in the non-common cache content set;

(3.5.4) for each satellite, updating the cache of the satellite to a common cache content set and cache revenue maximization content in a non-common cache content set;

(3.5.5) calculating the average content service delay of the system after the cache strategy is updated;

(3.5.6) judging whether the average content service delay after updating the cache strategy is the same as the average content service delay before updating;

(3.5.7) if the two are the same, ending the iteration;

(3.5.8) if the difference is not the same, repeating the iteration process until the iteration is finished.

Images